© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35345
    Prev
    Next
    INDEX
    Explanations

    unexpected situations and strangers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rptr
    -1.10
     originalmente
    -1.07
     primeros
    -1.05
    LCA
    -1.04
     sometimes
    -1.02
    やかな
    -1.02
     was
    -1.01
     often
    -1.00
     Testamento
    -1.00
     cucharadita
    -0.99
    POSITIVE LOGITS
     kullanılır
    1.13
     ofreció
    1.08
    ૅ
    1.03
     莫
    0.98
     a
    0.96
    ֮
    0.96
     pick
    0.94
     geschieht
    0.94
    意外
    0.91
     entregó
    0.91
    Activations Density 0.066%

    No Known Activations